Chaoyu Zhang
Virginia Tech - Graduate Research Assistant
About
I am currently a Ph.D. student in Computer Science at Virginia Tech, under the supervision of Professor Wenjing Lou.
My research is dedicated to exploring the native security challenges of AI innovations and how AI can be leveraged to enhance security. It encompasses Large Language Models (watermarking for IP protection, adversarial example attacks, jailbreak exploits), Federated Learning Systems (privacy leakage, defense mechanisms, Byzantine resiliency), AI-Driven Network Security (machine learning-based intrusion detection systems), and Heterogeneous Computing (cryptographic and machine learning applications).
Education
- Ph.D. in Computer Science, Virginia Tech (VT), 2021-now
- M.S. in Computer Science, Arkansas State University (ASU), 2018-2021
- B.E. in Electronic Engineering, Beijing University of Posts and Telecommunications (BUPT), 2014-2018
News
- -[Feb. 2025] Our paper ‘MedLeak: Harvesting Multimodal Medical Data in Secure Federated Learning with Crafted Models’, was accepted by the IEEE/ACM Conference on Connected Health: Applications, Systems, and Engineering Technologies (CHASE 2025).
- -[Feb. 2025] Our paper ‘StarCast: A Secure and Spectrum-Efficient Group Communication Scheme for LEO Satellite Networks’, was accepted by the IEEE International Symposium on Dynamic Spectrum Access Networks (DySPAN 2025).
- -[Dec. 2024] Our paper 'FLARE: Defending Federated Learning against Model Poisoning Attacks via Latent Space Representations', was accepted by the IEEE Transactions on Dependable and Secure Computing (TDSC).
- -[Nov. 2024] Our paper ‘Scale-MIA: A Scalable Model Inversion Attack against Secure Federated Learning via Latent Space Reconstruction’, was accepted by the Network and Distributed System Security Symposium (NDSS 2025).
- -[Aug. 2024] Our paper ‘ProFLingo: A Fingerprinting-based Intellectual Property Protection Scheme for Large Language Models’, won best paper award at the IEEE Conference on Communications and Network Security 2024 (CNS 2024).
- -[Aug. 2024] Our paper ‘ProFLingo: A Fingerprinting-based Intellectual Property Protection Scheme for Large Language Models’, was accepted by the IEEE Conference on Communications and Network Security 2024 (CNS 2024).
- -[Aug. 2024] Our paper ‘Hermes: Boosting the Performance of Machine-Learning-Based Intrusion Detection System through Geometric Feature Learning’, was accepted by the 25th International Symposium on Theory, Algorithmic Foundations, and Protocol Design for Mobile Networks and Mobile Computing (MobiHoc 2024).
- -[Aug. 2023] Our paper ‘MINDFL: Mitigating the Impact of Imbalanced and Noisy-labeled Data in Federated Learning with Quality and Fairness-Aware Client Selection’ was accepted by the IEEE Military Communications Conference (MILCOM 2023).
- -[Aug. 2023] Our paper ‘Bijack: Breaking Bitcoin Network with TCP Vulnerabilities’ was accepted by the 28th European Symposium on Research in Computer Security (ESORICS 2023).
Publications
- Shanghao Shi, Md Shahedul Haque, Abhijeet Parida, Marius Linguraru, Chaoyu Zhang, Y. Thomas Hou, Syed Anwar, and Wenjing Lou. “MedLeak: Harvesting Multimodal Medical Data in Secure Federated Learning with Crafted Models”, IEEE/ACM CHASE 2025.
- Chaoyu Zhang, Hexuan Yu, Shanghao Shi, Shaoyu Li, Yi Shi, Eric Burger, Y. Thomas Hou, Wenjing Lou, "StarCast: Securing Multicast Communications in LEO Satellite Networks", IEEE Dyspan 2025.
- Chaoyu Zhang, Shanghao Shi, Ning Wang, Xiangxiang Xu, Shaoyu Li, L. Zheng, R. Marchany, M. Gardner, Wenjing Lou, Y. Thomas Hou, "Hermes: Boosting the Performance of Machine-Learning-based Intrusion Detection System through Geometric Feature Learning", ACM MobiHoc 2024.
- Heng Jin, Chaoyu Zhang, Shanghao Shi, Thomas Hou, Wenjing Lou, "ProFLingo: A Fingerprinting-based Copyright Protection Scheme for Large Language Models", IEEE CNS 2024
- Shanghao Shi, Ning Wang, Y. Xiao, Chaoyu Zhang, Y. Shi, Y. Thomas Hou, Wenjing Lou, "Scale-MIA: A Scalable Model Inversion Attack against Secure Federated Learning via Latent Space Reconstruction", NDSS 2025.
- Chaoyu Zhang, Ning Wang, Shanghao Shi, Changlai Du, Wenjing Lou, Y. Thomas Hou, "MINDFL: Mitigating the Impact of Imbalanced and Noisy-Labeled Data in Federated Learning with Quality and Fairness-Aware Client Selection", IEEE MILCOM 2023.
- Shaoyu Li, Shanghao Shi, Yang Xiao, Chaoyu Zhang, Y. Thomas Hou, Wenjing Lou, "Bijack: Breaking Bitcoin Network with TCP Vulnerabilities", ESORICS 2023.
- Ning Wang, Chaoyu Zhang, Y. Xiao, Y. Chen, Wenjing Lou, Y. Thomas Hou, "FLARE: Defending Federated Learning against Model Poisoning Attacks via Latent Space Representations", IEEE Transactions on Dependable and Secure Computing. IEEE TDSC
- Ruipeng Li, Chaoyu Zhang, "Efficient parallel implementations of sparse triangular solves for GPU architectures", SIAM PP 2020.
- Chaoyu Zhang, Hexuan Yu, Yuchen Zhou, Hai Jiang, "High-Performance and Energy-Efficient FPGA-GPU-CPU Heterogeneous System Implementation", PDPTA 2020.
- Hexuan Yu, Chaoyu Zhang, Hai Jiang, "A FPGA-based Heterogeneous Implementation of NTRUEncrypt", PDPTA 2020.
- Chaoyu Zhang, Ruipeng Li, Hai Jiang, "Optimization of GPU Kernels for Sparse Matrix Computations in Hypre", Poster, SC 2019.
- Kai Fan, Chaoyu Zhang, Ruiwen Shan, Hexuan Yu and Hai Jiang, "GPU Acceleration of Ciphertext-Policy Attributed-Based Encryption", IEEE SNPD 2019.
Awards and Honors
Best Paper Award
IEEE Conference on Communications and Network Security 2024
Student Travel Grant
IEEE Military Communications Conference 2023
ACM Student Research Competition Travel Grant 2019
Supercomputing (SC'19)
Excellent Thesis Award
Beijing University of Posts and Telecommunications 2018
Second-Class Prize, BUPT Innovation Project 2016
Short Distance Wireless Storage and Sharing System
Academic Services
Workshop (Web Specialist / Volunteer):
NSF CISE CAREER Workshop:
2023,
2024,
2025
ARO Workshop on AI for Security and Security of AI, 2023
Reviewer / Sub-Reviewer:
Conference: IEEE SP 23, 24, 25; ACM CCS 23; IEEE INFOCOM 25; ACM WiSec 23, 24, 25; IEEE CNS 24; IEEE MILCOM 24; ESORICS 23, 24; IEEE ICCCN 23
Journal: IEEE TIFS; IEEE TON; IEEE TNSE; IEEE TCPS; IEEE IOTJ